Proposal of automated computational method to support Virginia tobacco classification/ Proposta de metodo computacional automatizado para apoio a classificacao de tabaco Virginia

This article proposes an automatic method for classification of cured tobacco leaves. Typically this process is performed manually, allowing the occurrence of human errors. In addition, the existence of an automated comparative procedure, helping to perform the classification, can make this process...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Revista brasileira de engenharia agrícola e ambiental 2019-10, Vol.23 (10), p.782
Hauptverfasser: Tedesco, Leonel P.C, de Freitas, Adriano da C, Molz, Rolf F, Schreiber, Jacques N.C
Format: Artikel
Sprache:spa
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue 10
container_start_page 782
container_title Revista brasileira de engenharia agrícola e ambiental
container_volume 23
creator Tedesco, Leonel P.C
de Freitas, Adriano da C
Molz, Rolf F
Schreiber, Jacques N.C
description This article proposes an automatic method for classification of cured tobacco leaves. Typically this process is performed manually, allowing the occurrence of human errors. In addition, the existence of an automated comparative procedure, helping to perform the classification, can make this process faster and more transparent. In order to implement the method, non-invasive to the agricultural product, 250 samples of Virginia tobacco digital images in the RGB and HSV color models were analyzed. The validation of the method was carried out using partial least squares (PLS) and artificial neural network (ANN), presenting a qualitative and quantitative analysis of both tools. It has been verified that the PLS can be applied to this method, as it has a shorter computational time, better suiting a real-time process. It can be verified that the ANN obtained better prediction results. Both methods employed had better results when adopting the RGB color model, reaching coefficient of determinations of 68 and 96% for the PLS and ANN methods, respectively. Key words: image processing, partial least square, artificial neural network Este artigo propoe um metodo automatico para classificacao de folhas de tabaco curado. Tipicamente este processo e realizado de modo manual, possibilitando erros humanos. Aliado a isso, a existencia de um procedimento comparativo automatizado, auxiliando na realizacao da classificacao, podera tornar tal processo mais rapido e transparente. Para a implementacao do metodo, nao invasivo ao produto agricola, analisou-se 250 amostras de imagens digitais de tabaco Virginia nos modelos de cores RGB e HSV A validacao do metodo foi desenvolvida empregando ferramentas de quadrados minimos parciais (QMP) e rede neural artificial (RNA), apresentando uma analise qualitativa e quantitativa de ambos as ferramentas. Verificou-se que a tecnica de QMP pode ser aplicada para este metodo, pelo fato de possuir um tempo computacional menor, adequando-se melhor a um processo em tempo real. Pode-se constatar que o metodo por RNA obteve melhores resultados de predicao. Ambos os metodos empregados, tiveram melhores resultados adotando o modelo de cor RGB, atingindo coeficientes de determinacao de 68 e 96% para o metodo de QMP e RNA, respectivamente. Palavras-chave: processamento de imagem, quadrados minimos parciais, rede neural artificial
doi_str_mv 10.1590/1807-1929/agriambi.v23n10p782-786
format Article
fullrecord <record><control><sourceid>gale</sourceid><recordid>TN_cdi_gale_infotracmisc_A604170617</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><galeid>A604170617</galeid><sourcerecordid>A604170617</sourcerecordid><originalsourceid>FETCH-LOGICAL-g677-8fb09f1c914512a8373ba20cda85269b14a4fd525ca31abceb18197b7cebc3933</originalsourceid><addsrcrecordid>eNptjc1OwzAQhH0AiVJ4B0ucOKT1xomdHKuKP6kSHCqu1dpxglGTjRKXA4_FE-LSgnpAe9jVzM43jN2CmEFeijkUQidQpuUcm8Fja_zsI5UdiF4XaaILdcYmkEGeZFKpC3Y5ju9C5BqUmrCvl4F6GnHLqea4C9RicBW31Pa7gMFTF63WhTeqeCA-7vqehsBf_dD4zmPUDFpL3G5xHH3t7U9mzg_YgLxy-zhV9Mu0B-axy39itHockGNPnjieoCzSPh8wdtBf5xU7r3E7uuvjnrL1_d16-Zisnh-elotV0iitk6I2oqzBlpDlkGIhtTSYClthkaeqNJBhVld5mluUgMY6AwWU2uh4WVlKOWU3B2yDW7fxXU1hQNv60W4WSmSghQIdv2b_fMWpXOstda72UT8JfAO6yIpc</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Proposal of automated computational method to support Virginia tobacco classification/ Proposta de metodo computacional automatizado para apoio a classificacao de tabaco Virginia</title><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><creator>Tedesco, Leonel P.C ; de Freitas, Adriano da C ; Molz, Rolf F ; Schreiber, Jacques N.C</creator><creatorcontrib>Tedesco, Leonel P.C ; de Freitas, Adriano da C ; Molz, Rolf F ; Schreiber, Jacques N.C</creatorcontrib><description>This article proposes an automatic method for classification of cured tobacco leaves. Typically this process is performed manually, allowing the occurrence of human errors. In addition, the existence of an automated comparative procedure, helping to perform the classification, can make this process faster and more transparent. In order to implement the method, non-invasive to the agricultural product, 250 samples of Virginia tobacco digital images in the RGB and HSV color models were analyzed. The validation of the method was carried out using partial least squares (PLS) and artificial neural network (ANN), presenting a qualitative and quantitative analysis of both tools. It has been verified that the PLS can be applied to this method, as it has a shorter computational time, better suiting a real-time process. It can be verified that the ANN obtained better prediction results. Both methods employed had better results when adopting the RGB color model, reaching coefficient of determinations of 68 and 96% for the PLS and ANN methods, respectively. Key words: image processing, partial least square, artificial neural network Este artigo propoe um metodo automatico para classificacao de folhas de tabaco curado. Tipicamente este processo e realizado de modo manual, possibilitando erros humanos. Aliado a isso, a existencia de um procedimento comparativo automatizado, auxiliando na realizacao da classificacao, podera tornar tal processo mais rapido e transparente. Para a implementacao do metodo, nao invasivo ao produto agricola, analisou-se 250 amostras de imagens digitais de tabaco Virginia nos modelos de cores RGB e HSV A validacao do metodo foi desenvolvida empregando ferramentas de quadrados minimos parciais (QMP) e rede neural artificial (RNA), apresentando uma analise qualitativa e quantitativa de ambos as ferramentas. Verificou-se que a tecnica de QMP pode ser aplicada para este metodo, pelo fato de possuir um tempo computacional menor, adequando-se melhor a um processo em tempo real. Pode-se constatar que o metodo por RNA obteve melhores resultados de predicao. Ambos os metodos empregados, tiveram melhores resultados adotando o modelo de cor RGB, atingindo coeficientes de determinacao de 68 e 96% para o metodo de QMP e RNA, respectivamente. Palavras-chave: processamento de imagem, quadrados minimos parciais, rede neural artificial</description><identifier>ISSN: 1415-4366</identifier><identifier>DOI: 10.1590/1807-1929/agriambi.v23n10p782-786</identifier><language>spa</language><publisher>ATECEL--Associacao Tecnico Cientifica Ernesto Luiz de Oliveira Junior</publisher><subject>Agricultural products ; Artificial neural networks ; Backup software ; Comparative analysis ; Image processing ; Methods ; RNA ; Technology application</subject><ispartof>Revista brasileira de engenharia agrícola e ambiental, 2019-10, Vol.23 (10), p.782</ispartof><rights>COPYRIGHT 2019 ATECEL--Associacao Tecnico Cientifica Ernesto Luiz de Oliveira Junior</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,777,781,27905,27906</link.rule.ids></links><search><creatorcontrib>Tedesco, Leonel P.C</creatorcontrib><creatorcontrib>de Freitas, Adriano da C</creatorcontrib><creatorcontrib>Molz, Rolf F</creatorcontrib><creatorcontrib>Schreiber, Jacques N.C</creatorcontrib><title>Proposal of automated computational method to support Virginia tobacco classification/ Proposta de metodo computacional automatizado para apoio a classificacao de tabaco Virginia</title><title>Revista brasileira de engenharia agrícola e ambiental</title><description>This article proposes an automatic method for classification of cured tobacco leaves. Typically this process is performed manually, allowing the occurrence of human errors. In addition, the existence of an automated comparative procedure, helping to perform the classification, can make this process faster and more transparent. In order to implement the method, non-invasive to the agricultural product, 250 samples of Virginia tobacco digital images in the RGB and HSV color models were analyzed. The validation of the method was carried out using partial least squares (PLS) and artificial neural network (ANN), presenting a qualitative and quantitative analysis of both tools. It has been verified that the PLS can be applied to this method, as it has a shorter computational time, better suiting a real-time process. It can be verified that the ANN obtained better prediction results. Both methods employed had better results when adopting the RGB color model, reaching coefficient of determinations of 68 and 96% for the PLS and ANN methods, respectively. Key words: image processing, partial least square, artificial neural network Este artigo propoe um metodo automatico para classificacao de folhas de tabaco curado. Tipicamente este processo e realizado de modo manual, possibilitando erros humanos. Aliado a isso, a existencia de um procedimento comparativo automatizado, auxiliando na realizacao da classificacao, podera tornar tal processo mais rapido e transparente. Para a implementacao do metodo, nao invasivo ao produto agricola, analisou-se 250 amostras de imagens digitais de tabaco Virginia nos modelos de cores RGB e HSV A validacao do metodo foi desenvolvida empregando ferramentas de quadrados minimos parciais (QMP) e rede neural artificial (RNA), apresentando uma analise qualitativa e quantitativa de ambos as ferramentas. Verificou-se que a tecnica de QMP pode ser aplicada para este metodo, pelo fato de possuir um tempo computacional menor, adequando-se melhor a um processo em tempo real. Pode-se constatar que o metodo por RNA obteve melhores resultados de predicao. Ambos os metodos empregados, tiveram melhores resultados adotando o modelo de cor RGB, atingindo coeficientes de determinacao de 68 e 96% para o metodo de QMP e RNA, respectivamente. Palavras-chave: processamento de imagem, quadrados minimos parciais, rede neural artificial</description><subject>Agricultural products</subject><subject>Artificial neural networks</subject><subject>Backup software</subject><subject>Comparative analysis</subject><subject>Image processing</subject><subject>Methods</subject><subject>RNA</subject><subject>Technology application</subject><issn>1415-4366</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><recordid>eNptjc1OwzAQhH0AiVJ4B0ucOKT1xomdHKuKP6kSHCqu1dpxglGTjRKXA4_FE-LSgnpAe9jVzM43jN2CmEFeijkUQidQpuUcm8Fja_zsI5UdiF4XaaILdcYmkEGeZFKpC3Y5ju9C5BqUmrCvl4F6GnHLqea4C9RicBW31Pa7gMFTF63WhTeqeCA-7vqehsBf_dD4zmPUDFpL3G5xHH3t7U9mzg_YgLxy-zhV9Mu0B-axy39itHockGNPnjieoCzSPh8wdtBf5xU7r3E7uuvjnrL1_d16-Zisnh-elotV0iitk6I2oqzBlpDlkGIhtTSYClthkaeqNJBhVld5mluUgMY6AwWU2uh4WVlKOWU3B2yDW7fxXU1hQNv60W4WSmSghQIdv2b_fMWpXOstda72UT8JfAO6yIpc</recordid><startdate>20191001</startdate><enddate>20191001</enddate><creator>Tedesco, Leonel P.C</creator><creator>de Freitas, Adriano da C</creator><creator>Molz, Rolf F</creator><creator>Schreiber, Jacques N.C</creator><general>ATECEL--Associacao Tecnico Cientifica Ernesto Luiz de Oliveira Junior</general><scope>INF</scope></search><sort><creationdate>20191001</creationdate><title>Proposal of automated computational method to support Virginia tobacco classification/ Proposta de metodo computacional automatizado para apoio a classificacao de tabaco Virginia</title><author>Tedesco, Leonel P.C ; de Freitas, Adriano da C ; Molz, Rolf F ; Schreiber, Jacques N.C</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-g677-8fb09f1c914512a8373ba20cda85269b14a4fd525ca31abceb18197b7cebc3933</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>spa</language><creationdate>2019</creationdate><topic>Agricultural products</topic><topic>Artificial neural networks</topic><topic>Backup software</topic><topic>Comparative analysis</topic><topic>Image processing</topic><topic>Methods</topic><topic>RNA</topic><topic>Technology application</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tedesco, Leonel P.C</creatorcontrib><creatorcontrib>de Freitas, Adriano da C</creatorcontrib><creatorcontrib>Molz, Rolf F</creatorcontrib><creatorcontrib>Schreiber, Jacques N.C</creatorcontrib><collection>Gale OneFile: Informe Academico</collection><jtitle>Revista brasileira de engenharia agrícola e ambiental</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tedesco, Leonel P.C</au><au>de Freitas, Adriano da C</au><au>Molz, Rolf F</au><au>Schreiber, Jacques N.C</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Proposal of automated computational method to support Virginia tobacco classification/ Proposta de metodo computacional automatizado para apoio a classificacao de tabaco Virginia</atitle><jtitle>Revista brasileira de engenharia agrícola e ambiental</jtitle><date>2019-10-01</date><risdate>2019</risdate><volume>23</volume><issue>10</issue><spage>782</spage><pages>782-</pages><issn>1415-4366</issn><abstract>This article proposes an automatic method for classification of cured tobacco leaves. Typically this process is performed manually, allowing the occurrence of human errors. In addition, the existence of an automated comparative procedure, helping to perform the classification, can make this process faster and more transparent. In order to implement the method, non-invasive to the agricultural product, 250 samples of Virginia tobacco digital images in the RGB and HSV color models were analyzed. The validation of the method was carried out using partial least squares (PLS) and artificial neural network (ANN), presenting a qualitative and quantitative analysis of both tools. It has been verified that the PLS can be applied to this method, as it has a shorter computational time, better suiting a real-time process. It can be verified that the ANN obtained better prediction results. Both methods employed had better results when adopting the RGB color model, reaching coefficient of determinations of 68 and 96% for the PLS and ANN methods, respectively. Key words: image processing, partial least square, artificial neural network Este artigo propoe um metodo automatico para classificacao de folhas de tabaco curado. Tipicamente este processo e realizado de modo manual, possibilitando erros humanos. Aliado a isso, a existencia de um procedimento comparativo automatizado, auxiliando na realizacao da classificacao, podera tornar tal processo mais rapido e transparente. Para a implementacao do metodo, nao invasivo ao produto agricola, analisou-se 250 amostras de imagens digitais de tabaco Virginia nos modelos de cores RGB e HSV A validacao do metodo foi desenvolvida empregando ferramentas de quadrados minimos parciais (QMP) e rede neural artificial (RNA), apresentando uma analise qualitativa e quantitativa de ambos as ferramentas. Verificou-se que a tecnica de QMP pode ser aplicada para este metodo, pelo fato de possuir um tempo computacional menor, adequando-se melhor a um processo em tempo real. Pode-se constatar que o metodo por RNA obteve melhores resultados de predicao. Ambos os metodos empregados, tiveram melhores resultados adotando o modelo de cor RGB, atingindo coeficientes de determinacao de 68 e 96% para o metodo de QMP e RNA, respectivamente. Palavras-chave: processamento de imagem, quadrados minimos parciais, rede neural artificial</abstract><pub>ATECEL--Associacao Tecnico Cientifica Ernesto Luiz de Oliveira Junior</pub><doi>10.1590/1807-1929/agriambi.v23n10p782-786</doi></addata></record>
fulltext fulltext
identifier ISSN: 1415-4366
ispartof Revista brasileira de engenharia agrícola e ambiental, 2019-10, Vol.23 (10), p.782
issn 1415-4366
language spa
recordid cdi_gale_infotracmisc_A604170617
source Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals
subjects Agricultural products
Artificial neural networks
Backup software
Comparative analysis
Image processing
Methods
RNA
Technology application
title Proposal of automated computational method to support Virginia tobacco classification/ Proposta de metodo computacional automatizado para apoio a classificacao de tabaco Virginia
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T04%3A37%3A41IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-gale&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Proposal%20of%20automated%20computational%20method%20to%20support%20Virginia%20tobacco%20classification/%20Proposta%20de%20metodo%20computacional%20automatizado%20para%20apoio%20a%20classificacao%20de%20tabaco%20Virginia&rft.jtitle=Revista%20brasileira%20de%20engenharia%20agr%C3%ADcola%20e%20ambiental&rft.au=Tedesco,%20Leonel%20P.C&rft.date=2019-10-01&rft.volume=23&rft.issue=10&rft.spage=782&rft.pages=782-&rft.issn=1415-4366&rft_id=info:doi/10.1590/1807-1929/agriambi.v23n10p782-786&rft_dat=%3Cgale%3EA604170617%3C/gale%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_galeid=A604170617&rfr_iscdi=true